279 citations · 685 across the 70 of their papers we have counts for
77 papers · 1 filter
Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation
Kartik Kartik, Sanjana Soni, Anoop Kunchukuttan +2
The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This…
Understanding the role of FFNs in driving multilingual behaviour in LLMs
Sunit Bhattacharya, Ondřej Bojar
Multilingualism in Large Language Models (LLMs) is an yet under-explored area. In this paper, we conduct an in-depth analysis of the multilingual capabilities of a family of a Larg…
Quality and Quantity of Machine Translation References for Automatic Metrics
Vilém Zouhar, Ondřej Bojar
Automatic machine translation metrics typically rely on human translations to determine the quality of system translations. Common wisdom in the field dictates that the human refer…
Evaluating Optimal Reference Translations
Vilém Zouhar, Věra Kloudová, Martin Popel +1
The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not sui…
Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networks
Sunit Bhattacharya, Ondrej Bojar
Recent research suggests that the feed-forward module within Transformers can be viewed as a collection of key-value memories, where the keys learn to capture specific patterns fro…
Boosting Unsupervised Machine Translation with Pseudo-Parallel Data
Ivana Kvapilíková, Ondřej Bojar
Even with the latest developments in deep learning and large-scale language modeling, the task of machine translation (MT) of low-resource languages remains a challenge. Neural MT…
Long-Form End-to-End Speech Translation via Latent Alignment Segmentation
Peter Polák, Ondřej Bojar
Current simultaneous speech translation models can process audio only up to a few seconds long. Contemporary datasets provide an oracle segmentation into sentences based on human-a…
Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff
Peter Polák, Brian Yan, Shinji Watanabe +2
Blockwise self-attentional encoder models have recently emerged as one promising end-to-end approach to simultaneous speech translation. These models employ a blockwise beam search…
Minuteman: Machine and Human Joining Forces in Meeting Summarization
František Kmječ, Ondřej Bojar
Many meetings require creating a meeting summary to keep everyone up to date. Creating minutes of sufficient quality is however very cognitively demanding. Although we currently po…
Character-level NMT and language similarity
Josef Jon, Ondřej Bojar
We explore the effectiveness of character-level neural machine translation using Transformer architecture for various levels of language similarity and size of the training dataset…
Negative Lexical Constraints in Neural Machine Translation
Josef Jon, Dušan Variš, Michal Novák +2
This paper explores negative lexical constraining in English to Czech neural machine translation. Negative lexical constraining is used to prohibit certain words or expressions in…
Turning Whisper into Real-Time Transcription System
Dominik Macháček, Raj Dabre, Ondřej Bojar
Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we bui…
Assessing Word Importance Using Models Trained for Semantic Tasks
Dávid Javorský, Ondřej Bojar, François Yvon
Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural…
Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation
Josef Jon, Ondřej Bojar
We propose a genetic algorithm (GA) based method for modifying n-best lists produced by a machine translation (MT) system. Our method offers an innovative approach to improving MT…
HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language
Shantipriya Parida, Idris Abdulmumin, Shamsuddeen Hassan Muhammad +7
This paper presents HaVQA, the first multimodal dataset for visual question-answering (VQA) tasks in the Hausa language. The dataset was created by manually translating 6,022 Engli…
Robustness of Multi-Source MT to Transcription Errors
Dominik Macháček, Peter Polák, Ondřej Bojar +1
Automatic speech translation is sensitive to speech recognition errors, but in a multilingual scenario, the same content may be available in various languages via simultaneous inte…
Multimodal Shannon Game with Images
Vilém Zouhar, Sunit Bhattacharya, Ondřej Bojar
The Shannon game has long been used as a thought experiment in linguistics and NLP, asking participants to guess the next letter in a sentence based on its preceding context. We ex…
CUNI Submission in WMT22 General Task
Josef Jon, Martin Popel, Ondřej Bojar
We present the CUNI-Bergamot submission for the WMT22 General translation task. We compete in EnglishCzech direction. Our submission further explores block backtransla…
MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation
Dominik Macháček, Ondřej Bojar, Raj Dabre
There have been several meta-evaluation studies on the correlation between human ratings and offline machine translation (MT) evaluation metrics such as BLEU, chrF2, BertScore and…
Simultaneous Translation for Unsegmented Input: A Sliding Window Approach
Sukanta Sen, Ondřej Bojar, Barry Haddow
In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is ty…
Sentence Ambiguity, Grammaticality and Complexity Probes
Sunit Bhattacharya, Vilém Zouhar, Ondřej Bojar
It is unclear whether, how and where large pre-trained language models capture subtle linguistic traits like ambiguity, grammaticality and sentence complexity. We present results o…
ALIGNMEET: A Comprehensive Tool for Meeting Annotation, Alignment, and Evaluation
Peter Polák, Muskaan Singh, Anna Nedoluzhko +1
Summarization is a challenging problem, and even more challenging is to manually create, correct, and evaluate the summaries. The severity of the problem grows when the inputs are…
CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022
Peter Polák, Ngoc-Quan Ngoc, Tuan-Nam Nguyen +5
In this paper, we describe our submission to the Simultaneous Speech Translation at IWSLT 2022. We explore strategies to utilize an offline model in a simultaneous setting without…
Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation
Idris Abdulmumin, Satya Ranjan Dash, Musa Abdullahi Dawud +7
Multi-modal Machine Translation (MMT) enables the use of visual information to enhance the quality of translations. The visual information can serve as a valuable piece of context…